recon-solar-installers

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs running curl/grep commands that extract and print API keys and sensitive values from JS and debug logs, which requires the agent to handle and output secrets verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is a targeted reconnaissance toolkit explicitly designed to discover and harvest sensitive data (SSNs, loan/applicant data, API keys) and to probe/abuse unauthenticated or CORS endpoints for unauthorized data exfiltration and credential access.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s runtime workflow uses curl to fetch arbitrary public web content from target domains (e.g., crt.sh JSON, /wp-content/debug.log, client JS, and other endpoints) and then pipes the fetched readable text into local processing (python3, grep, jq), which can include outsider-authored free text from those sites.